* [PATCH 6/9] net: ethernet: ti: cpsw: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Grygorii Strashko,
David S. Miller, linux-omap, netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/ethernet/ti/cpsw.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 16dcbf36f8cc..4753ae7178fb 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3658,8 +3658,7 @@ static int cpsw_remove(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int cpsw_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
if (cpsw->data.dual_emac) {
@@ -3682,8 +3681,7 @@ static int cpsw_suspend(struct device *dev)
static int cpsw_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
/* Select default pin state */
--
2.19.0
^ permalink raw reply related
* [PATCH 5/9] net: ethernet: smsc: smc91x: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Nicolas Pitre, David S. Miller,
netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/ethernet/smsc/smc91x.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index 8d6cff8bd162..4823b6a51134 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2447,8 +2447,7 @@ static int smc_drv_remove(struct platform_device *pdev)
static int smc_drv_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
if (ndev) {
if (netif_running(ndev)) {
--
2.19.0
^ permalink raw reply related
* [PATCH 4/9] net: ethernet: davicom: dm9000: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel; +Cc: linux-renesas-soc, Wolfram Sang, David S. Miller, netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/ethernet/davicom/dm9000.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 50222b7b81f3..0a82fcf16d35 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1722,8 +1722,7 @@ dm9000_probe(struct platform_device *pdev)
static int
dm9000_drv_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct board_info *db;
if (ndev) {
@@ -1745,8 +1744,7 @@ dm9000_drv_suspend(struct device *dev)
static int
dm9000_drv_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *ndev = platform_get_drvdata(pdev);
+ struct net_device *ndev = dev_get_drvdata(dev);
struct board_info *db = netdev_priv(ndev);
if (ndev) {
--
2.19.0
^ permalink raw reply related
* [PATCH 3/9] net: ethernet: cadence: macb_main: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Nicolas Ferre, David S. Miller,
netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/ethernet/cadence/macb_main.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 0acaef3ef548..8f5bf9166c11 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -4156,8 +4156,7 @@ static int macb_remove(struct platform_device *pdev)
static int __maybe_unused macb_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *netdev = platform_get_drvdata(pdev);
+ struct net_device *netdev = dev_get_drvdata(dev);
struct macb *bp = netdev_priv(netdev);
netif_carrier_off(netdev);
@@ -4179,8 +4178,7 @@ static int __maybe_unused macb_suspend(struct device *dev)
static int __maybe_unused macb_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct net_device *netdev = platform_get_drvdata(pdev);
+ struct net_device *netdev = dev_get_drvdata(dev);
struct macb *bp = netdev_priv(netdev);
if (bp->wol & MACB_WOL_ENABLED) {
--
2.19.0
^ permalink raw reply related
* [PATCH 1/9] net: dsa: bcm_sf2: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, netdev
In-Reply-To: <20181021200021.1693-1-wsa+renesas@sang-engineering.com>
We should get 'driver_data' from 'struct device' directly. Going via
platform_device is an unneeded step back and forth.
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
Build tested only. buildbot is happy.
drivers/net/dsa/bcm_sf2.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 3017ecf82ca5..2eb68769562c 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1190,16 +1190,14 @@ static void bcm_sf2_sw_shutdown(struct platform_device *pdev)
#ifdef CONFIG_PM_SLEEP
static int bcm_sf2_suspend(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct bcm_sf2_priv *priv = platform_get_drvdata(pdev);
+ struct bcm_sf2_priv *priv = dev_get_drvdata(dev);
return dsa_switch_suspend(priv->dev->ds);
}
static int bcm_sf2_resume(struct device *dev)
{
- struct platform_device *pdev = to_platform_device(dev);
- struct bcm_sf2_priv *priv = platform_get_drvdata(pdev);
+ struct bcm_sf2_priv *priv = dev_get_drvdata(dev);
return dsa_switch_resume(priv->dev->ds);
}
--
2.19.0
^ permalink raw reply related
* [PATCH 0/9] net: simplify getting .driver_data
From: Wolfram Sang @ 2018-10-21 20:00 UTC (permalink / raw)
To: linux-kernel
Cc: linux-renesas-soc, Wolfram Sang, linux-omap, linux-arm-kernel,
netdev
I got tired of fixing this in Renesas drivers manually, so I took the big
hammer. Remove this cumbersome code pattern which got copy-pasted too much
already:
- struct platform_device *pdev = to_platform_device(dev);
- struct ep93xx_keypad *keypad = platform_get_drvdata(pdev);
+ struct ep93xx_keypad *keypad = dev_get_drvdata(dev);
A branch, tested by buildbot, can be found here:
git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git coccinelle/get_drvdata
I have been asked if it couldn't be done for dev_set_drvdata as well. I checked
it and did not find one occasion where it could be simplified like this. Not
much of a surprise because driver_data is usually set in probe() functions
which access struct platform_device in many other ways.
I am open for other comments, suggestions, too, of course.
Here is the cocci-script I created:
@@
struct device* d;
identifier pdev;
expression *ptr;
@@
(
- struct platform_device *pdev = to_platform_device(d);
|
- struct platform_device *pdev;
...
- pdev = to_platform_device(d);
)
<... when != pdev
- &pdev->dev
+ d
...>
ptr =
- platform_get_drvdata(pdev)
+ dev_get_drvdata(d)
<... when != pdev
- &pdev->dev
+ d
...>
Kind regards,
Wolfram
Wolfram Sang (9):
net: dsa: bcm_sf2: simplify getting .driver_data
net: dsa: qca8k: simplify getting .driver_data
net: ethernet: cadence: macb_main: simplify getting .driver_data
net: ethernet: davicom: dm9000: simplify getting .driver_data
net: ethernet: smsc: smc91x: simplify getting .driver_data
net: ethernet: ti: cpsw: simplify getting .driver_data
net: ethernet: ti: davinci_emac: simplify getting .driver_data
net: ethernet: wiznet: w5300: simplify getting .driver_data
net: phy: mdio-mux-bcm-iproc: simplify getting .driver_data
drivers/net/dsa/bcm_sf2.c | 6 ++----
drivers/net/dsa/qca8k.c | 6 ++----
drivers/net/ethernet/cadence/macb_main.c | 6 ++----
drivers/net/ethernet/davicom/dm9000.c | 6 ++----
drivers/net/ethernet/smsc/smc91x.c | 3 +--
drivers/net/ethernet/ti/cpsw.c | 6 ++----
drivers/net/ethernet/ti/davinci_emac.c | 6 ++----
drivers/net/ethernet/wiznet/w5300.c | 6 ++----
drivers/net/phy/mdio-mux-bcm-iproc.c | 6 ++----
9 files changed, 17 insertions(+), 34 deletions(-)
--
2.19.0
^ permalink raw reply
* Re: [PATCH] net/mlx5: allocate enough space in
From: Or Gerlitz @ 2018-10-21 10:56 UTC (permalink / raw)
To: Dan Carpenter
Cc: Saeed Mahameed, Paul Blakey, kernel-janitors, Linux Netdev List,
Leon Romanovsky
In-Reply-To: <CAJ3xEMhwcYYDWWLropG95T6TyE62OfJS+oPAFDZKLOVJSurNRQ@mail.gmail.com>
On Sat, Oct 20, 2018 at 11:37 PM Or Gerlitz <gerlitz.or@gmail.com> wrote:
> On Fri, Oct 19, 2018 at 11:08 PM Dan Carpenter <dan.carpenter@oracle.com> wrote:
> > FDB_MAX_CHAIN is 3. We wanted to allocate enough memory to hold four
> > structs but there are missing parentheses so we only allocate enough
> > memory for three structs and the first byte of the fourth one.
>
> yeah, seems that we were wrong here and the fix is correct, at some
> point I saw Kasan screams but it was gone later, let me look, thanks for pointing it out.
OK, here's the kasan note:
[ 289.005141] BUG: KASAN: slab-out-of-bounds in
mlx5_init_fs+0x6a7/0x1176 [mlx5_core]
[ 289.005244] Write of size 8 at addr ffff8806cfb70e58 by task modprobe/6186
my .config was like this w.r.t kasan:
CONFIG_KASAN_SHADOW_OFFSET=0xdffffc0000000000
CONFIG_HAVE_ARCH_KASAN=y
CONFIG_KASAN=y
# CONFIG_KASAN_EXTRA is not set
CONFIG_KASAN_OUTLINE=y
# CONFIG_KASAN_INLINE is not set
# CONFIG_TEST_KASAN is not set
where now, when I changed it to be:
CONFIG_KASAN_SHADOW_OFFSET=0xdffffc0000000000
CONFIG_HAVE_ARCH_KASAN=y
CONFIG_KASAN=y
CONFIG_KASAN_EXTRA=y
# CONFIG_KASAN_OUTLINE is not set
CONFIG_KASAN_INLINE=y
# CONFIG_TEST_KASAN is not set
Kasan is there to spot the bug.
I will re-post your patch, this time to netdev since the original
commit is there
and so should be the fix, thanks for reporting/fixing!
Or.
^ permalink raw reply
* I NEED YOUR HELP URGENTLY!!!
From: GEN KELVIN @ 2018-10-21 0:26 UTC (permalink / raw)
To: Recipients
Compliment of the day to you. I am Gen.Kelvin W Howard, I am sending this brief letter to solicit your partnership of Sixteen Million Two Hundred Thousand United States Dollars ($16,200,000). I shall send you more information and procedures when I receive positive response from you.Best Regards,
CONTACT ME: kivenhoward@gmail.com
Gen.Kelvin W Howard
---
This email has been checked for viruses by Avast antivirus software.
https://www.avast.com/antivirus
^ permalink raw reply
* Re: [PATCH net-next] octeontx2-af: Remove set but not used variable 'block'
From: YueHaibing @ 2018-10-21 10:07 UTC (permalink / raw)
To: Sunil Kovvuri
Cc: Sunil Goutham, Linu Cherian, Geetha sowjanya, jerinj,
David S. Miller, Linux Netdev List, kernel-janitors
In-Reply-To: <CA+sq2CekhmaVQddoy2T0e5B9KwG2=_8d+KVFavqfnJfAFSPs2A@mail.gmail.com>
On 2018/10/19 21:36, Sunil Kovvuri wrote:
> On Fri, Oct 19, 2018 at 6:11 PM YueHaibing <yuehaibing@huawei.com> wrote:
>>
>> Fixes gcc '-Wunused-but-set-variable' warning:
>>
>> drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c: In function 'rvu_npa_init':
>> drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c:446:20: warning:
>> variable 'block' set but not used [-Wunused-but-set-variable]
>>
>> It never used since introduction in
>> commit 7a37245ef23f ("octeontx2-af: NPA block admin queue init")
>>
>> Signed-off-by: YueHaibing <yuehaibing@huawei.com>
>> ---
>> drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c | 3 ---
>> 1 file changed, 3 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
>> index 0e43a69..7531fdc 100644
>> --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
>> +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
>> @@ -443,15 +443,12 @@ static int npa_aq_init(struct rvu *rvu, struct rvu_block *block)
>> int rvu_npa_init(struct rvu *rvu)
>> {
>> struct rvu_hwinfo *hw = rvu->hw;
>> - struct rvu_block *block;
>> int blkaddr, err;
>>
>> blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPA, 0);
>> if (blkaddr < 0)
>> return 0;
>>
>> - block = &hw->block[blkaddr];
>> -
>> /* Initialize admin queue */
>> err = npa_aq_init(rvu, &hw->block[blkaddr]);
>> if (err)
>>
>
> Thanks for the patch.
> Which GCC version do you use ?
gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.10)
> Before submitting patches I did test compiling specifically with these
> "make arch=X86 -j8 -Werror=unused-function -Wunused-but-set-variable"
> but that didn't throw these warnings.
>
> Thanks,
> Sunil.
>
> .
>
^ permalink raw reply
* Re: [PATCH bpf-next] selftests/bpf: enable (uncomment) all tests in test_libbpf.sh
From: Jesper Dangaard Brouer @ 2018-10-21 9:57 UTC (permalink / raw)
To: Quentin Monnet
Cc: Alexei Starovoitov, Daniel Borkmann, netdev, oss-drivers, brouer
In-Reply-To: <1540072824-27914-1-git-send-email-quentin.monnet@netronome.com>
On Sat, 20 Oct 2018 23:00:24 +0100
Quentin Monnet <quentin.monnet@netronome.com> wrote:
> libbpf is now able to load successfully test_l4lb_noinline.o and
> samples/bpf/tracex3_kern.o, so we can uncomment related tests from
> test_libbpf.c and remove the associated "TODO"s.
Thanks for working on this, comments below.
> It is also trivial to fix test_xdp_noinline.o so that it provides a
> version and can be loaded. Fix it and uncomment this test as well.
>
> For the record, the error message obtainted with tracex3_kern.o was
> fixed by commit e3d91b0ca523 ("tools/libbpf: handle issues with bpf ELF
> objects containing .eh_frames")
>
> I have not been abled to reproduce the "libbpf: incorrect bpf_call
> opcode" error for test_l4lb_noinline.o, even with the version of libbpf
> present at the time when test_libbpf.sh and test_libbpf_open.c were
> created.
>
> Cc: Jesper Dangaard Brouer <brouer@redhat.com>
> Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
> ---
> tools/testing/selftests/bpf/test_libbpf.sh | 12 +++---------
> tools/testing/selftests/bpf/test_xdp_meta.c | 2 ++
> 2 files changed, 5 insertions(+), 9 deletions(-)
>
> diff --git a/tools/testing/selftests/bpf/test_libbpf.sh b/tools/testing/selftests/bpf/test_libbpf.sh
> index 156d89f1edcc..a426f28163a5 100755
> --- a/tools/testing/selftests/bpf/test_libbpf.sh
> +++ b/tools/testing/selftests/bpf/test_libbpf.sh
> @@ -33,17 +33,11 @@ trap exit_handler 0 2 3 6 9
>
> libbpf_open_file test_l4lb.o
>
> -# TODO: fix libbpf to load noinline functions
> -# [warning] libbpf: incorrect bpf_call opcode
> -#libbpf_open_file test_l4lb_noinline.o
> +libbpf_open_file test_l4lb_noinline.o
>
> -# TODO: fix test_xdp_meta.c to load with libbpf
> -# [warning] libbpf: test_xdp_meta.o doesn't provide kernel version
> -#libbpf_open_file test_xdp_meta.o
> +libbpf_open_file test_xdp_meta.o
>
> -# TODO: fix libbpf to handle .eh_frame
> -# [warning] libbpf: relocation failed: no section(10)
> -#libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
> +libbpf_open_file ../../../../samples/bpf/tracex3_kern.o
I don't like the ../../../../samples/bpf/ reference (even-through I
added this TODO), as the kselftests AFAIK support installing the
selftests and then this tests will fail.
Maybe we can find another example kern.o file?
(which isn't compiled with -target bpf)
> # Success
> exit 0
> diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/test_xdp_meta.c
> index 8d0182650653..2f42de66e2bb 100644
> --- a/tools/testing/selftests/bpf/test_xdp_meta.c
> +++ b/tools/testing/selftests/bpf/test_xdp_meta.c
> @@ -8,6 +8,8 @@
> #define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
> #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
>
> +int _version SEC("version") = 1;
> +
> SEC("t")
> int ing_cls(struct __sk_buff *ctx)
> {
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* r8169: changed rx buffer alignment requirement
From: Heiner Kallweit @ 2018-10-21 9:02 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev@vger.kernel.org
Hi Eric,
when working on the r8169 driver I came across an old patch from you:
6f0333b8fde4 ("r8169: use 50% less ram for RX ring")
As part of this patch the alignment requirement for rx buffers was
silently changed from 8 to 16 bytes. Can you remember (well, after
eight years) why you did this? In the chip datasheet I find only
8 bytes mentioned as requirement.
Regards,
Heiner
^ permalink raw reply
* Re: [PATCH] net: ethernet:fec: Consistently use SPEED_ prefix
From: Sergei Shtylyov @ 2018-10-21 8:25 UTC (permalink / raw)
To: Andrew Lunn, David Miller; +Cc: clabbe, netdev, Florian Fainelli, hkallweit1
In-Reply-To: <1540068491-14760-1-git-send-email-andrew@lunn.ch>
On 20.10.2018 23:48, Andrew Lunn wrote:
> All other calls to phy_set_max_speed() use the SPEED_ prefix. Make the
> FEC driver follow this common pattern. This makes no different to
Difference.
> generated code since SPEED_1000 is 1000, and SPEED_100 is 100.
>
> Reported-by: Corentin Labbe <clabbe@baylibre.com>
> Signed-off-by: Andrew Lunn <andrew@lunn.ch>
[...]
MBR, Sergei
^ permalink raw reply
* Re: [PATCH net-next] net: phy: phy_support_sym_pause: Clear Asym Pause
From: Sergei Shtylyov @ 2018-10-21 8:24 UTC (permalink / raw)
To: Andrew Lunn, clabbe, David Miller; +Cc: netdev, Florian Fainelli, hkallweit1
In-Reply-To: <1540068088-14446-1-git-send-email-andrew@lunn.ch>
Hello!
On 20.10.2018 23:41, Andrew Lunn wrote:
> When indicating the MAC supports Symmetric Pause, clear the Asymmetric
> Pause bit, which could of been already set is the PHY supports it.
Could've been, s/is/if/.
> Reported-by: Labbe Corentin <clabbe@baylibre.com>
> Fixes: c306ad36184f ("net: ethernet: Add helper for MACs which support pause")
> Signed-off-by: Andrew Lunn <andrew@lunn.ch>
[...]
MBR, Sergei
^ permalink raw reply
* Re: [PATCH net-next 0/3] sctp: add support for sk_reuseport
From: Xin Long @ 2018-10-21 6:58 UTC (permalink / raw)
To: network dev, linux-sctp; +Cc: Marcelo Ricardo Leitner, Neil Horman, davem
In-Reply-To: <cover.1540095102.git.lucien.xin@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 3812 bytes --]
On Sun, Oct 21, 2018 at 1:43 PM Xin Long <lucien.xin@gmail.com> wrote:
>
> sctp sk_reuseport allows multiple socks to listen on the same port and
> addresses, as long as these socks have the same uid. This works pretty
> much as TCP/UDP does, the only difference is that sctp is multi-homing
> and all the bind_addrs in these socks will have to completely matched,
> otherwise listen() will return err.
>
> The below is when 5 sockets are listening on 172.16.254.254:6400 on a
> server, 26 sockets on a client connect to 172.16.254.254:6400 and each
> may be processed by a different socket on the server which is selected
> by hash(lport, pport, paddr) in reuseport_select_sock():
>
> # ss --sctp -nn
> State Recv-Q Send-Q Local Address:Port Peer Address:Port
> LISTEN 0 10 172.16.254.254:6400 *:*
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.1:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.4:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.3:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.4:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.2:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.3:1234
> LISTEN 0 10 172.16.254.254:6400 *:*
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.3:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.4:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.2:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.1:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.2:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.3:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.4:1234
> LISTEN 0 10 172.16.254.254:6400 *:*
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.2:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.5:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.5:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.253.253:1234
> LISTEN 0 10 172.16.254.254:6400 *:*
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.2:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.3:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.4:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.5:1234
> LISTEN 0 10 172.16.254.254:6400 *:*
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.1:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.5:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.5:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.1:1234
> `- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.1:1234
Attached is the testcase based on sctp-tests.git.
>
> Xin Long (3):
> sctp: do reuseport_select_sock in __sctp_rcv_lookup_endpoint
> sctp: add sock_reuseport for the sock in __sctp_hash_endpoint
> sctp: process sk_reuseport in sctp_get_port_local
>
> include/net/sctp/sctp.h | 2 +-
> include/net/sctp/structs.h | 6 ++-
> net/core/sock_reuseport.c | 1 +
> net/sctp/bind_addr.c | 28 ++++++++++
> net/sctp/input.c | 129 ++++++++++++++++++++++++++++++++-------------
> net/sctp/socket.c | 49 +++++++++++------
> 6 files changed, 162 insertions(+), 53 deletions(-)
>
> --
> 2.1.0
>
[-- Attachment #2: reuseport.tar.gz --]
[-- Type: application/x-gzip, Size: 2501 bytes --]
^ permalink raw reply
* Re: [PATCH net-next] net: phy: phy_support_sym_pause: Clear Asym Pause
From: LABBE Corentin @ 2018-10-21 6:54 UTC (permalink / raw)
To: Andrew Lunn; +Cc: David Miller, netdev, Florian Fainelli, hkallweit1
In-Reply-To: <1540068088-14446-1-git-send-email-andrew@lunn.ch>
On Sat, Oct 20, 2018 at 10:41:28PM +0200, Andrew Lunn wrote:
> When indicating the MAC supports Symmetric Pause, clear the Asymmetric
> Pause bit, which could of been already set is the PHY supports it.
>
> Reported-by: Labbe Corentin <clabbe@baylibre.com>
> Fixes: c306ad36184f ("net: ethernet: Add helper for MACs which support pause")
> Signed-off-by: Andrew Lunn <andrew@lunn.ch>
> ---
> drivers/net/phy/phy_device.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
> index 43cb08dcce81..ab33d1777132 100644
> --- a/drivers/net/phy/phy_device.c
> +++ b/drivers/net/phy/phy_device.c
> @@ -1940,6 +1940,7 @@ EXPORT_SYMBOL(phy_remove_link_mode);
> */
> void phy_support_sym_pause(struct phy_device *phydev)
> {
> + phydev->supported &= ~SUPPORTED_Asym_Pause;
> phydev->supported |= SUPPORTED_Pause;
> phydev->advertising = phydev->supported;
> }
> --
> 2.19.0
>
Thanks, it made my imx6q-sabrelite works again with next-20181019.
Tested-by: Corentin Labbe <clabbe@baylibre.com>
For completeness, this is the ethtool output which confirm it.
ethtool version 4.16
Settings for eth0:
Supported ports: [ TP MII ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Supported pause frame use: Symmetric
Supports auto-negotiation: Yes
Supported FEC modes: Not reported
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Advertised pause frame use: Symmetric
Advertised auto-negotiation: Yes
Advertised FEC modes: Not reported
Link partner advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Half 1000baseT/Full
Link partner advertised pause frame use: Symmetric Receive-only
Link partner advertised auto-negotiation: Yes
Link partner advertised FEC modes: Not reported
Speed: 1000Mb/s
Duplex: Full
Port: MII
PHYAD: 6
Transceiver: internal
Auto-negotiation: on
Supports Wake-on: d
Wake-on: d
Link detected: yes
^ permalink raw reply
* Re: [PATCH bpf-next 0/3] tools: bpftool: bring minor fixes to bpftool
From: Alexei Starovoitov @ 2018-10-21 6:22 UTC (permalink / raw)
To: Quentin Monnet; +Cc: Alexei Starovoitov, Daniel Borkmann, netdev, oss-drivers
In-Reply-To: <1540072910-29732-1-git-send-email-quentin.monnet@netronome.com>
On Sat, Oct 20, 2018 at 11:01:47PM +0100, Quentin Monnet wrote:
> Hi,
> These are three minor fixes for bpftool, its documentation and its bash
> completion function. Please refer to individual patches for details.
Applied, Thanks
^ permalink raw reply
* Re: [PATCH bpf-next] selftests/bpf: fix return value comparison for tests in test_libbpf.sh
From: Alexei Starovoitov @ 2018-10-21 6:19 UTC (permalink / raw)
To: Quentin Monnet; +Cc: Alexei Starovoitov, Daniel Borkmann, netdev, oss-drivers
In-Reply-To: <1540072724-26002-1-git-send-email-quentin.monnet@netronome.com>
On Sat, Oct 20, 2018 at 10:58:44PM +0100, Quentin Monnet wrote:
> The return value for each test in test_libbpf.sh is compared with
>
> if (( $? == 0 )) ; then ...
>
> This works well with bash, but not with dash, that /bin/sh is aliased to
> on some systems (such as Ubuntu).
>
> Let's replace this comparison by something that works on both shells.
>
> Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Applied, Thanks
^ permalink raw reply
* Re: [PATCH bpf-next 0/6] Misc improvements and few minor fixes
From: Alexei Starovoitov @ 2018-10-21 6:18 UTC (permalink / raw)
To: Daniel Borkmann; +Cc: netdev
In-Reply-To: <20181021000928.15705-1-daniel@iogearbox.net>
On Sun, Oct 21, 2018 at 02:09:22AM +0200, Daniel Borkmann wrote:
> Last batch of misc patches I had in queue: first one removes some left-over
> bits from ULP, second is a fix in the verifier where we wrongly use register
> number as type to fetch the string for the dump, third disables xadd on flow
> keys and subsequent one removes the flow key type from check_helper_mem_access()
> as they cannot be passed into any helper as of today. Next one lets map push,
> pop, peek avoid having to go through retpoline, and last one has a couple of
> minor fixes and cleanups for the ring buffer walk.
Applied, Thanks
^ permalink raw reply
* Re: [PATCH net] Revert "neighbour: force neigh_invalidate when NUD_FAILED update is from admin"
From: David Miller @ 2018-10-21 5:26 UTC (permalink / raw)
To: roopa; +Cc: netdev
In-Reply-To: <1540084171-12793-1-git-send-email-roopa@cumulusnetworks.com>
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Sat, 20 Oct 2018 18:09:31 -0700
> From: Roopa Prabhu <roopa@cumulusnetworks.com>
>
> This reverts commit 8e326289e3069dfc9fa9c209924668dd031ab8ef.
>
> This patch results in unnecessary netlink notification when one
> tries to delete a neigh entry already in NUD_FAILED state. Found
> this with a buggy app that tries to delete a NUD_FAILED entry
> repeatedly. While the notification issue can be fixed with more
> checks, adding more complexity here seems unnecessary. Also,
> recent tests with other changes in the neighbour code have
> shown that the INCOMPLETE and PROBE checks are good enough for
> the original issue.
>
> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Applied, thanks.
^ permalink raw reply
* [PATCH net-next 3/3] sctp: process sk_reuseport in sctp_get_port_local
From: Xin Long @ 2018-10-21 4:43 UTC (permalink / raw)
To: network dev, linux-sctp; +Cc: Marcelo Ricardo Leitner, Neil Horman, davem
In-Reply-To: <cover.1540095102.git.lucien.xin@gmail.com>
When socks' sk_reuseport is set, the same port and address are allowed
to be bound into these socks who have the same uid.
Note that the difference from sk_reuse is that it allows multiple socks
to listen on the same port and address.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/net/sctp/structs.h | 4 +++-
net/sctp/socket.c | 46 +++++++++++++++++++++++++++++++++-------------
2 files changed, 36 insertions(+), 14 deletions(-)
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 15d017f..af9d494 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -96,7 +96,9 @@ struct sctp_stream;
struct sctp_bind_bucket {
unsigned short port;
- unsigned short fastreuse;
+ signed char fastreuse;
+ signed char fastreuseport;
+ kuid_t fastuid;
struct hlist_node node;
struct hlist_head owner;
struct net *net;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 44e7d8c..8605705 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7642,8 +7642,10 @@ static struct sctp_bind_bucket *sctp_bucket_create(
static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
{
- bool reuse = (sk->sk_reuse || sctp_sk(sk)->reuse);
+ struct sctp_sock *sp = sctp_sk(sk);
+ bool reuse = (sk->sk_reuse || sp->reuse);
struct sctp_bind_hashbucket *head; /* hash list */
+ kuid_t uid = sock_i_uid(sk);
struct sctp_bind_bucket *pp;
unsigned short snum;
int ret;
@@ -7719,7 +7721,10 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
pr_debug("%s: found a possible match\n", __func__);
- if (pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING)
+ if ((pp->fastreuse && reuse &&
+ sk->sk_state != SCTP_SS_LISTENING) ||
+ (pp->fastreuseport && sk->sk_reuseport &&
+ uid_eq(pp->fastuid, uid)))
goto success;
/* Run through the list of sockets bound to the port
@@ -7733,16 +7738,18 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
* in an endpoint.
*/
sk_for_each_bound(sk2, &pp->owner) {
- struct sctp_endpoint *ep2;
- ep2 = sctp_sk(sk2)->ep;
+ struct sctp_sock *sp2 = sctp_sk(sk2);
+ struct sctp_endpoint *ep2 = sp2->ep;
if (sk == sk2 ||
- (reuse && (sk2->sk_reuse || sctp_sk(sk2)->reuse) &&
- sk2->sk_state != SCTP_SS_LISTENING))
+ (reuse && (sk2->sk_reuse || sp2->reuse) &&
+ sk2->sk_state != SCTP_SS_LISTENING) ||
+ (sk->sk_reuseport && sk2->sk_reuseport &&
+ uid_eq(uid, sock_i_uid(sk2))))
continue;
- if (sctp_bind_addr_conflict(&ep2->base.bind_addr, addr,
- sctp_sk(sk2), sctp_sk(sk))) {
+ if (sctp_bind_addr_conflict(&ep2->base.bind_addr,
+ addr, sp2, sp)) {
ret = (long)sk2;
goto fail_unlock;
}
@@ -7765,19 +7772,32 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
pp->fastreuse = 1;
else
pp->fastreuse = 0;
- } else if (pp->fastreuse &&
- (!reuse || sk->sk_state == SCTP_SS_LISTENING))
- pp->fastreuse = 0;
+
+ if (sk->sk_reuseport) {
+ pp->fastreuseport = 1;
+ pp->fastuid = uid;
+ } else {
+ pp->fastreuseport = 0;
+ }
+ } else {
+ if (pp->fastreuse &&
+ (!reuse || sk->sk_state == SCTP_SS_LISTENING))
+ pp->fastreuse = 0;
+
+ if (pp->fastreuseport &&
+ (!sk->sk_reuseport || !uid_eq(pp->fastuid, uid)))
+ pp->fastreuseport = 0;
+ }
/* We are set, so fill up all the data in the hash table
* entry, tie the socket list information with the rest of the
* sockets FIXME: Blurry, NPI (ipg).
*/
success:
- if (!sctp_sk(sk)->bind_hash) {
+ if (!sp->bind_hash) {
inet_sk(sk)->inet_num = snum;
sk_add_bind_node(sk, &pp->owner);
- sctp_sk(sk)->bind_hash = pp;
+ sp->bind_hash = pp;
}
ret = 0;
--
2.1.0
^ permalink raw reply related
* [PATCH net-next 2/3] sctp: add sock_reuseport for the sock in __sctp_hash_endpoint
From: Xin Long @ 2018-10-21 4:43 UTC (permalink / raw)
To: network dev, linux-sctp; +Cc: Marcelo Ricardo Leitner, Neil Horman, davem
In-Reply-To: <cover.1540095102.git.lucien.xin@gmail.com>
This is a part of sk_reuseport support for sctp. It defines a helper
sctp_bind_addrs_check() to check if the bind_addrs in two socks are
matched. It will add sock_reuseport if they are completely matched,
and return err if they are partly matched, and alloc sock_reuseport
if all socks are not matched at all.
It will work until sk_reuseport support is added in
sctp_get_port_local() in the next patch.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
include/net/sctp/sctp.h | 2 +-
include/net/sctp/structs.h | 2 ++
net/core/sock_reuseport.c | 1 +
net/sctp/bind_addr.c | 28 ++++++++++++++++++++++
net/sctp/input.c | 60 +++++++++++++++++++++++++++++++++++++++-------
net/sctp/socket.c | 3 +--
6 files changed, 85 insertions(+), 11 deletions(-)
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 8c2caa3..b8cd58d 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -152,7 +152,7 @@ int sctp_primitive_RECONF(struct net *net, struct sctp_association *asoc,
*/
int sctp_rcv(struct sk_buff *skb);
void sctp_v4_err(struct sk_buff *skb, u32 info);
-void sctp_hash_endpoint(struct sctp_endpoint *);
+int sctp_hash_endpoint(struct sctp_endpoint *ep);
void sctp_unhash_endpoint(struct sctp_endpoint *);
struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *,
struct sctphdr *, struct sctp_association **,
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index a11f937..15d017f 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1190,6 +1190,8 @@ int sctp_bind_addr_conflict(struct sctp_bind_addr *, const union sctp_addr *,
struct sctp_sock *, struct sctp_sock *);
int sctp_bind_addr_state(const struct sctp_bind_addr *bp,
const union sctp_addr *addr);
+int sctp_bind_addrs_check(struct sctp_sock *sp,
+ struct sctp_sock *sp2, int cnt2);
union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp,
const union sctp_addr *addrs,
int addrcnt,
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index ba5cba5..d8fe3e5 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -187,6 +187,7 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
call_rcu(&old_reuse->rcu, reuseport_free_rcu);
return 0;
}
+EXPORT_SYMBOL(reuseport_add_sock);
void reuseport_detach_sock(struct sock *sk)
{
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 7df3704..78d0d93 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -337,6 +337,34 @@ int sctp_bind_addr_match(struct sctp_bind_addr *bp,
return match;
}
+int sctp_bind_addrs_check(struct sctp_sock *sp,
+ struct sctp_sock *sp2, int cnt2)
+{
+ struct sctp_bind_addr *bp2 = &sp2->ep->base.bind_addr;
+ struct sctp_bind_addr *bp = &sp->ep->base.bind_addr;
+ struct sctp_sockaddr_entry *laddr, *laddr2;
+ bool exist = false;
+ int cnt = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(laddr, &bp->address_list, list) {
+ list_for_each_entry_rcu(laddr2, &bp2->address_list, list) {
+ if (sp->pf->af->cmp_addr(&laddr->a, &laddr2->a) &&
+ laddr->valid == laddr2->valid) {
+ exist = true;
+ goto next;
+ }
+ }
+ cnt = 0;
+ break;
+next:
+ cnt++;
+ }
+ rcu_read_unlock();
+
+ return (cnt == cnt2) ? 0 : (exist ? -EEXIST : 1);
+}
+
/* Does the address 'addr' conflict with any addresses in
* the bp.
*/
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 60ede89..6bfeb10 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -723,43 +723,87 @@ static int sctp_rcv_ootb(struct sk_buff *skb)
}
/* Insert endpoint into the hash table. */
-static void __sctp_hash_endpoint(struct sctp_endpoint *ep)
+static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
{
- struct net *net = sock_net(ep->base.sk);
- struct sctp_ep_common *epb;
+ struct sock *sk = ep->base.sk;
+ struct net *net = sock_net(sk);
struct sctp_hashbucket *head;
+ struct sctp_ep_common *epb;
epb = &ep->base;
-
epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
head = &sctp_ep_hashtable[epb->hashent];
+ if (sk->sk_reuseport) {
+ bool any = sctp_is_ep_boundall(sk);
+ struct sctp_ep_common *epb2;
+ struct list_head *list;
+ int cnt = 0, err = 1;
+
+ list_for_each(list, &ep->base.bind_addr.address_list)
+ cnt++;
+
+ sctp_for_each_hentry(epb2, &head->chain) {
+ struct sock *sk2 = epb2->sk;
+
+ if (!net_eq(sock_net(sk2), net) || sk2 == sk ||
+ !uid_eq(sock_i_uid(sk2), sock_i_uid(sk)) ||
+ !sk2->sk_reuseport)
+ continue;
+
+ err = sctp_bind_addrs_check(sctp_sk(sk2),
+ sctp_sk(sk), cnt);
+ if (!err) {
+ err = reuseport_add_sock(sk, sk2, any);
+ if (err)
+ return err;
+ break;
+ } else if (err < 0) {
+ return err;
+ }
+ }
+
+ if (err) {
+ err = reuseport_alloc(sk, any);
+ if (err)
+ return err;
+ }
+ }
+
write_lock(&head->lock);
hlist_add_head(&epb->node, &head->chain);
write_unlock(&head->lock);
+ return 0;
}
/* Add an endpoint to the hash. Local BH-safe. */
-void sctp_hash_endpoint(struct sctp_endpoint *ep)
+int sctp_hash_endpoint(struct sctp_endpoint *ep)
{
+ int err;
+
local_bh_disable();
- __sctp_hash_endpoint(ep);
+ err = __sctp_hash_endpoint(ep);
local_bh_enable();
+
+ return err;
}
/* Remove endpoint from the hash table. */
static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
{
- struct net *net = sock_net(ep->base.sk);
+ struct sock *sk = ep->base.sk;
struct sctp_hashbucket *head;
struct sctp_ep_common *epb;
epb = &ep->base;
- epb->hashent = sctp_ep_hashfn(net, epb->bind_addr.port);
+ epb->hashent = sctp_ep_hashfn(sock_net(sk), epb->bind_addr.port);
head = &sctp_ep_hashtable[epb->hashent];
+ if (rcu_access_pointer(sk->sk_reuseport_cb))
+ reuseport_detach_sock(sk);
+
write_lock(&head->lock);
hlist_del_init(&epb->node);
write_unlock(&head->lock);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fc0386e..44e7d8c 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -7850,8 +7850,7 @@ static int sctp_listen_start(struct sock *sk, int backlog)
}
sk->sk_max_ack_backlog = backlog;
- sctp_hash_endpoint(ep);
- return 0;
+ return sctp_hash_endpoint(ep);
}
/*
--
2.1.0
^ permalink raw reply related
* [PATCH net-next 1/3] sctp: do reuseport_select_sock in __sctp_rcv_lookup_endpoint
From: Xin Long @ 2018-10-21 4:43 UTC (permalink / raw)
To: network dev, linux-sctp; +Cc: Marcelo Ricardo Leitner, Neil Horman, davem
In-Reply-To: <cover.1540095102.git.lucien.xin@gmail.com>
This is a part of sk_reuseport support for sctp, and it selects a
sock by the hashkey of lport, paddr and dport by default. It will
work until sk_reuseport support is added in sctp_get_port_local()
in the next patch.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
---
net/sctp/input.c | 69 +++++++++++++++++++++++++++++++++-----------------------
1 file changed, 41 insertions(+), 28 deletions(-)
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 5c36a99..60ede89 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -57,6 +57,7 @@
#include <net/sctp/checksum.h>
#include <net/net_namespace.h>
#include <linux/rhashtable.h>
+#include <net/sock_reuseport.h>
/* Forward declarations for internal helpers. */
static int sctp_rcv_ootb(struct sk_buff *);
@@ -65,8 +66,10 @@ static struct sctp_association *__sctp_rcv_lookup(struct net *net,
const union sctp_addr *paddr,
const union sctp_addr *laddr,
struct sctp_transport **transportp);
-static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
- const union sctp_addr *laddr);
+static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(
+ struct net *net, struct sk_buff *skb,
+ const union sctp_addr *laddr,
+ const union sctp_addr *daddr);
static struct sctp_association *__sctp_lookup_association(
struct net *net,
const union sctp_addr *local,
@@ -171,7 +174,7 @@ int sctp_rcv(struct sk_buff *skb)
asoc = __sctp_rcv_lookup(net, skb, &src, &dest, &transport);
if (!asoc)
- ep = __sctp_rcv_lookup_endpoint(net, &dest);
+ ep = __sctp_rcv_lookup_endpoint(net, skb, &dest, &src);
/* Retrieve the common input handling substructure. */
rcvr = asoc ? &asoc->base : &ep->base;
@@ -770,16 +773,35 @@ void sctp_unhash_endpoint(struct sctp_endpoint *ep)
local_bh_enable();
}
+static inline __u32 sctp_hashfn(const struct net *net, __be16 lport,
+ const union sctp_addr *paddr, __u32 seed)
+{
+ __u32 addr;
+
+ if (paddr->sa.sa_family == AF_INET6)
+ addr = jhash(&paddr->v6.sin6_addr, 16, seed);
+ else
+ addr = (__force __u32)paddr->v4.sin_addr.s_addr;
+
+ return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
+ (__force __u32)lport, net_hash_mix(net), seed);
+}
+
/* Look up an endpoint. */
-static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
- const union sctp_addr *laddr)
+static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(
+ struct net *net, struct sk_buff *skb,
+ const union sctp_addr *laddr,
+ const union sctp_addr *paddr)
{
struct sctp_hashbucket *head;
struct sctp_ep_common *epb;
struct sctp_endpoint *ep;
+ struct sock *sk;
+ __be32 lport;
int hash;
- hash = sctp_ep_hashfn(net, ntohs(laddr->v4.sin_port));
+ lport = laddr->v4.sin_port;
+ hash = sctp_ep_hashfn(net, ntohs(lport));
head = &sctp_ep_hashtable[hash];
read_lock(&head->lock);
sctp_for_each_hentry(epb, &head->chain) {
@@ -791,6 +813,15 @@ static struct sctp_endpoint *__sctp_rcv_lookup_endpoint(struct net *net,
ep = sctp_sk(net->sctp.ctl_sock)->ep;
hit:
+ sk = ep->base.sk;
+ if (sk->sk_reuseport) {
+ __u32 phash = sctp_hashfn(net, lport, paddr, 0);
+
+ sk = reuseport_select_sock(sk, phash, skb,
+ sizeof(struct sctphdr));
+ if (sk)
+ ep = sctp_sk(sk)->ep;
+ }
sctp_endpoint_hold(ep);
read_unlock(&head->lock);
return ep;
@@ -829,35 +860,17 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg,
static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed)
{
const struct sctp_transport *t = data;
- const union sctp_addr *paddr = &t->ipaddr;
- const struct net *net = sock_net(t->asoc->base.sk);
- __be16 lport = htons(t->asoc->base.bind_addr.port);
- __u32 addr;
-
- if (paddr->sa.sa_family == AF_INET6)
- addr = jhash(&paddr->v6.sin6_addr, 16, seed);
- else
- addr = (__force __u32)paddr->v4.sin_addr.s_addr;
- return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
- (__force __u32)lport, net_hash_mix(net), seed);
+ return sctp_hashfn(sock_net(t->asoc->base.sk),
+ htons(t->asoc->base.bind_addr.port),
+ &t->ipaddr, seed);
}
static inline __u32 sctp_hash_key(const void *data, u32 len, u32 seed)
{
const struct sctp_hash_cmp_arg *x = data;
- const union sctp_addr *paddr = x->paddr;
- const struct net *net = x->net;
- __be16 lport = x->lport;
- __u32 addr;
-
- if (paddr->sa.sa_family == AF_INET6)
- addr = jhash(&paddr->v6.sin6_addr, 16, seed);
- else
- addr = (__force __u32)paddr->v4.sin_addr.s_addr;
- return jhash_3words(addr, ((__force __u32)paddr->v4.sin_port) << 16 |
- (__force __u32)lport, net_hash_mix(net), seed);
+ return sctp_hashfn(x->net, x->lport, x->paddr, seed);
}
static const struct rhashtable_params sctp_hash_params = {
--
2.1.0
^ permalink raw reply related
* [PATCH net-next 0/3] sctp: add support for sk_reuseport
From: Xin Long @ 2018-10-21 4:43 UTC (permalink / raw)
To: network dev, linux-sctp; +Cc: Marcelo Ricardo Leitner, Neil Horman, davem
sctp sk_reuseport allows multiple socks to listen on the same port and
addresses, as long as these socks have the same uid. This works pretty
much as TCP/UDP does, the only difference is that sctp is multi-homing
and all the bind_addrs in these socks will have to completely matched,
otherwise listen() will return err.
The below is when 5 sockets are listening on 172.16.254.254:6400 on a
server, 26 sockets on a client connect to 172.16.254.254:6400 and each
may be processed by a different socket on the server which is selected
by hash(lport, pport, paddr) in reuseport_select_sock():
# ss --sctp -nn
State Recv-Q Send-Q Local Address:Port Peer Address:Port
LISTEN 0 10 172.16.254.254:6400 *:*
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.1:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.4:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.3:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.4:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.2:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.3:1234
LISTEN 0 10 172.16.254.254:6400 *:*
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.3:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.4:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.2:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.1:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.2:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.3:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.4:1234
LISTEN 0 10 172.16.254.254:6400 *:*
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.2:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.5:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.4.5:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.253.253:1234
LISTEN 0 10 172.16.254.254:6400 *:*
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.2:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.3:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.4:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.5:1234
LISTEN 0 10 172.16.254.254:6400 *:*
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.1:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.1.5:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.2.5:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.3.1:1234
`- ESTAB 0 0 172.16.254.254%eth1:6400 172.16.5.1:1234
Xin Long (3):
sctp: do reuseport_select_sock in __sctp_rcv_lookup_endpoint
sctp: add sock_reuseport for the sock in __sctp_hash_endpoint
sctp: process sk_reuseport in sctp_get_port_local
include/net/sctp/sctp.h | 2 +-
include/net/sctp/structs.h | 6 ++-
net/core/sock_reuseport.c | 1 +
net/sctp/bind_addr.c | 28 ++++++++++
net/sctp/input.c | 129 ++++++++++++++++++++++++++++++++-------------
net/sctp/socket.c | 49 +++++++++++------
6 files changed, 162 insertions(+), 53 deletions(-)
--
2.1.0
^ permalink raw reply
* Re: [PATCH] net: socket: fix a missing-check bug
From: Florian Fainelli @ 2018-10-21 3:21 UTC (permalink / raw)
To: Wenwen Wang; +Cc: Kangjie Lu, David S. Miller, netdev, linux-kernel
In-Reply-To: <1540051091-16604-1-git-send-email-wang6495@umn.edu>
Hi Wenwen,
On October 20, 2018 8:58:10 AM PDT, Wenwen Wang <wang6495@umn.edu> wrote:
>In ethtool_ioctl(), the ioctl command is firstly obtained from the
>user-space buffer 'compat_rxnfc' through get_user() and saved to
>'ethcmd'.
>Then, 'ethcmd' is checked to see whether it is necessary to pre-process
>the
>ethool structure, because the structure ethtool_rxnfc is defined with
>padding, as mentioned in the comment. If yes, a user-space buffer
>'rxnfc'
>is allocated through compat_alloc_user_space() and then the data in the
>original buffer 'compat_rxnfc' is copied to 'rxnfc' through
>copy_in_user(),
>including the ioctl command. It is worth noting that after this copy,
>there
>is no check enforced on the copied ioctl command. That means it is
>possible
>that 'rxnfc->cmd' is different from 'ethcmd', because a malicious user
>can
>race to modify the ioctl command in 'compat_rxnfc' between these two
>copies. Eventually, the ioctl command in 'rxnfc' will be used in
>dev_ethtool(). This can cause undefined behavior of the kernel and
>introduce potential security risk.
>
>This patch avoids the above issue by rewriting 'rxnfc->cmd' using
>'ethcmd'
>after copy_in_user().
>
>Signed-off-by: Wenwen Wang <wang6495@umn.edu>
Assuming these issues are found with some kind of automated analysis, can you also add in your work flow to provide a Fixes: tag such that this could be backported to stable kernels?
If this is found by a tool is this something that is open source and somehow available? I would also make it clear that these issues are typically named time TOCTOU which might be clearer for people who review those patches.
Thanks!
--
Florian
^ permalink raw reply
* [PATCH] af_unix.h: trivial whitespace cleanup
From: Vito Caputo @ 2018-10-21 11:33 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel
Replace spurious spaces with a tab and remove superfluous tab from
unix_sock struct.
Signed-off-by: Vito Caputo <vcaputo@pengaru.com>
---
include/net/af_unix.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index a5ba41b3b867..e2695c4bf358 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -52,7 +52,7 @@ struct unix_skb_parms {
struct unix_sock {
/* WARNING: sk has to be the first member */
struct sock sk;
- struct unix_address *addr;
+ struct unix_address *addr;
struct path path;
struct mutex iolock, bindlock;
struct sock *peer;
@@ -63,7 +63,7 @@ struct unix_sock {
#define UNIX_GC_CANDIDATE 0
#define UNIX_GC_MAYBE_CYCLE 1
struct socket_wq peer_wq;
- wait_queue_entry_t peer_wake;
+ wait_queue_entry_t peer_wake;
};
static inline struct unix_sock *unix_sk(const struct sock *sk)
--
2.11.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox